A systematic approach for segmenting voiced/unvoiced signals using fuzzy-logic system and general fusion of neural network models for phonemes-based speech recognition.
Sathees Kumar NatarajMurugesa Pandiyan PaulrajAhmad Nazri Bin AbdullahSazali Bin YaacobPublished in: J. Intell. Fuzzy Syst. (2020)
Keyphrases
- speech recognition
- speech signal
- neural network model
- speech processing
- noisy environments
- spectral analysis
- automatic speech recognition
- speaker identification
- hidden markov models
- speech synthesis
- background noise
- pattern recognition
- signal processing
- neural network
- vocal tract
- sound source
- linear prediction
- speech recognition systems
- language model
- speech recognizer
- cepstral coefficients
- non stationary
- speech enhancement
- image processing
- artificial neural networks
- neural models
- text to speech
- multilayer perceptron
- speaker independent
- speaker adaptation
- speech recognition technology